aiqbench analysis
This paper reframes prompting as a form of dialogic cognitive programming where natural language acts as an executable specification within distributed human-AI memory architectures. It proposes "Dialogic Working Memory" to explain how conversational states sustain reasoning continuity and regulate hybrid workflows, moving beyond classical NLP's focus on mere understanding. The work establishes a theoretical foundation for treating prompts as dynamic cognitive artefacts that externalize goals and intermediate reasoning states in generative AI systems.
Natural Language Programming: Rethinking Language, Memory, and Cognition in the Era of Generative AI
From arXiv
Full textarXiv:2611.23106v1 Announce Type: cross Abstract: Generative Artificial Intelligence is transforming the role of natural language in computational systems. In classical Natural Language Processing (NLP), language was treated as an object of computation: something to analyse, classify, translate, or generate. Large Language Models (LLMs) challenge this perspective, enabling natural language to function increasingly as an executable cognitive medium through which humans structure reasoning, orchestrate problem solving, and regulate hybrid human/AI workflows.
This paper introduces Natural Language Programming (NLPg) as a theoretical and epistemological extension of traditional NLP. Rather than focusing on language understanding alone, NLPg conceptualises prompts as dynamic cognitive artefacts that externalise goals, constraints, assumptions, validation criteria, and intermediate reasoning states. Prompting is thus not merely a technical interaction technique, but a form of dialogic cognitive programming operating within distributed human/AI memory architectures. Building on theories of distributed cognition, extended mind, metacognition, and dialogic learning, the paper proposes the notion of Dialogic Working Memory, describing how prompts and conversational states function as temporary external memory structures supporting reasoning continuity and reflective regulation.
We further map existing memory architectures (BTMA, SKGE, RMR) onto this framework, illustrating how episodic, semantic, and metacognitive layers support long-horizon conversational coherence. Finally, implications for computational linguistics and AI/mediated knowledge systems are discussed, suggesting a post symbolic and post interface paradigm in which natural language operates simultaneously as communication medium, executable specification, cognitive scaffold, and distributed memory architecture.
Abstract:Generative Artificial Intelligence is transforming the role of natural language in computational systems. In classical Natural Language Processing (NLP), language was treated as an object of computation: something to analyse, classify, translate, or generate. Large Language Models (LLMs) challenge this perspective, enabling natural language to function increasingly as an executable cognitive medium through which humans structure reasoning, orchestrate problem solving, and regulate hybrid human/AI workflows. This paper introduces Natural Language Programming (NLPg) as a theoretical and epistemological extension of traditional NLP.
Rather than focusing on language understanding alone, NLPg conceptualises prompts as dynamic cognitive artefacts that externalise goals, constraints, assumptions, validation criteria, and intermediate reasoning states. Prompting is thus not merely a technical interaction technique, but a form of dialogic cognitive programming operating within distributed human/AI memory architectures. Building on theories of distributed cognition, extended mind, metacognition, and dialogic learning, the paper proposes the notion of Dialogic Working Memory, describing how prompts and conversational states function as temporary external memory structures supporting reasoning continuity and reflective regulation.
We further map existing memory architectures (BTMA, SKGE, RMR) onto this framework, illustrating how episodic, semantic, and metacognitive layers support long-horizon conversational coherence. Finally, implications for computational linguistics and AI/mediated knowledge systems are discussed, suggesting a post symbolic and post interface paradigm in which natural language operates simultaneously as communication medium, executable specification, cognitive scaffold, and distributed memory architecture.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
I.2.7; H.5.2; I.2.0
arXiv:2611.23106 [cs.CL]
(or arXiv:2611.23106v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2611.23106 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 327 words
Related coverage

Presentation: APIs for Agents: Rethinking API Programs in the MCP Era
InfoQ · Sep 23, 2026

Don’t just prompt AI — architect it: Introducing the Professional Agentic Architect Certification
Google Cloud Blog · Nov 11, 2026
Rethinking Pivot Programming Languages in Code Language Models
arXiv · Sep 22, 2026
Article: Your Next DSL Author is a Language Model
InfoQ · Sep 16, 2026